Deep Fence Estimation using Stereo Guidance and Adversarial Learning

Autor:	Mittal, Paritosh, Venkatesan, Shankar M, Veera, Viswanath, De, Aloknath
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition I.4
Druh dokumentu:	Working Paper
Popis:	People capture memorable images of events and exhibits that are often occluded by a wire mesh loosely termed as fence. Recent works in removing fence have limited performance due to the difficulty in initial fence segmentation. This work aims to accurately segment fence using a novel fence guidance mask (FM) generated from stereo image pair. This binary guidance mask contains deterministic cues about the structure of fence and is given as additional input to the deep fence estimation model. We also introduce a directional connectivity loss (DCL), which is used alongside adversarial loss to precisely detect thin wires. Experimental results obtained on real world scenarios demonstrate the superiority of proposed method over state-of-the-art techniques. Comment: It was previously submitted to IEEE ICIP 2020. A previous version was also submitted to BMVC 2019
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2007.01724 Zobrazit plný text záznamu View this record from Arxiv